Please use this identifier to cite or link to this item:
Type: Conference paper
Title: Automatic segmentation of human tibial cartilage
Author: Cheong, J.
Faggian, N.
Suter, D.
Cicuttini, F.
Citation: Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (SPPRA 07), Innsbruck, Austria, 14-16 February 2007 / R. Sablatnig, O. Scherzer (eds.): pp.368-373
Publisher: ACTA Press
Publisher Place: Calgary, Canada
Issue Date: 2007
ISBN: 9780889866461
Conference Name: IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (4th : 2007 : Innsbruck, Austria)
Editor: Sablatnig, R.
Scherzer, O.
Statement of
J. Cheong, N. Faggian, D. Suter, and F. Cicuttini
Abstract: Osteoarthritis is a chronic and crippling disease affecting an increasing number of people each year. With no known cure, it is expected to reach epidemic proportions in the near future. Accurate segmentation of knee cartilage from magnetic resonance imaging (MRI) scans facilitates the measurement of cartilage volume present in a patient's knee, thus enabling medical clinicians to detect the onset of osteoarthritis and also crucially, to study its effects. This paper presents a fully automated method for segmenting and measuring human tibial cartilage volume from MRI scans. The method uses a global search technique developed by Felzenszwalb [1], involving triangulated polygons as deformable templates to initialise a patch-based active appearance model (PAAM) [2]. The cartilage volume obtained from our automatic method is benchmarked against the current "gold standard" (cartilage volume measured using manual segmentation) as well as other semi-automatic methods. The results obtained are comparable to human manual segmentation.
Keywords: Segmentation
Description (link):
Appears in Collections:Aurora harvest 5
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.